hermes-agent v0.6.1

👩🏻‍💻 A Helm chart to run Hermes Agent on Kubernetes, community-powered, lightweight

Run Hermes Agent — a multi-provider LLM agent framework — on Kubernetes. Configure any provider Hermes supports (OpenAI, Anthropic, Gemini, OpenRouter, NVIDIA, or any OpenAI-compatible proxy such as LiteLLM/vLLM) entirely via values.yaml, with a built-in helm test health check.

---

AppVersion: v2026.6.19 — the Hermes Agent image this chart version deploys.

Install

Latest (Helm repo)

helm repo add hermes-agent https://jyje.github.io/hermes-agent-helm
helm repo update
helm upgrade --install hermes-agent hermes-agent/hermes-agent \
  --namespace hermes-agent --create-namespace \
  --set-string env.OPENAI_API_KEY='sk-...' \
  --wait

This version (v0.6.1)

helm upgrade --install hermes-agent hermes-agent/hermes-agent \
  --namespace hermes-agent --create-namespace \
  --version 0.6.1 \
  --set-string env.OPENAI_API_KEY='sk-...' \
  --wait

OCI

helm upgrade --install hermes-agent oci://ghcr.io/jyje/hermes-agent-helm/hermes-agent \
  --namespace hermes-agent --create-namespace \
  --version 0.6.1 \
  --set-string env.OPENAI_API_KEY='sk-...' \
  --wait

---

Changelog

Bug Fixes

• 🐛 bug(changelog): credit plain Conventional Commits (no gitmoji) too (9c9d9aa) — @jyje
• 🐛 bug(ci): stop implying full CI passed in the Discord notice (6f37a2c) — @jyje
• 🐛 bug(workflow/propose-release): drop redundant unreleased heading and stop false-crediting past PRs (ccb67a3) — @jyje

Documentation

• 📄 docs(ci): document the matrix test job and local script reuse (1127b60) — @jyje
• 📄 docs(chart): link "Hermes Agent" to its upstream repo (672436d) — @jyje
• 📄 docs(local-dev): note helm-docs verification after editing values.yaml (f9912c1) — @jyje

Build

• 🔨 build(ci): rename the default scenario to message (ce41b5e) — @jyje

Tests

• ✅ test(ci): run each validate-chart scenario on its own kind cluster (0db971a) — @jyje